At Rutgers School of Social Work, doctoral students are exploring how emerging technologies can be used to better understand and address some of society’s most pressing challenges.
This spring, students enrolled in AI & Spatial Data Science for Global Development, a Ph.D.-level course taught by Assistant Professor Dr. Woojin Jung, with instructional support from teaching assistants Dr. Emmanuel Alvarez and Vatsal Shah, applied artificial intelligence, machine learning, and geospatial analysis to investigate issues ranging from substance use treatment access and energy equity to public transit history and global AI engagement.
Designed as an interdisciplinary laboratory, the course introduces students to the rapidly evolving field of applied data science for global development and social welfare policy. Students work with innovative data sources, including satellite imagery, crowd-sourced maps, and social media data, to conduct granular needs assessments and support evidence-informed policy design and evaluation.
The course welcomes students from a wide range of disciplines, including social work, public policy, international development, computer and information science, economics, statistics, business management, and geography. Working in collaborative teams, students combine diverse expertise and perspectives to develop policy-relevant research projects and produce initial conference paper drafts.
A programming lab component provides hands-on training in Python, with supplementary use of QGIS for geospatial analysis. Guest lecturers also expose students to emerging applications of data science in global development and social policy.
By the end of the semester, students are expected to define and critically assess key concepts in data science, artificial intelligence, and machine learning; identify emerging data sources relevant to development and service access; apply machine learning and geospatial methods to social problems; evaluate the policy impact of AI-based predictions; and collaborate across disciplines to design and assess data-intensive policies and programs.
At the end of the semester, students presented their research projects, showcasing how computational approaches can illuminate real-world challenges in social welfare and global development.
Examining Treatment Access in New Jersey
One team, comprised of Ivania Martinez Zamora, Taylor Scott, and Malya Hirshkowitz, examined Regional Disparities in Substance Use Treatment Access for Medicare Beneficiaries in New Jersey. Their project explored geographic inequities in substance use treatment availability among older adults and sought to identify underserved areas across the state.
“Dr. Jung’s elective course provided us with foundational skills in geospatial analysis, specifically aligned with social work projects,” the team shared. “Each of us within this group brought different skills and experience, since the class drew students from different disciplines, programs, and years across the university, which allowed us to learn from one another.”
“As a student in the social work Ph.D program, I appreciated the opportunity to broaden my methodological skillset within Rutgers School of Social Work and hope to continue honing my understanding of geospatial analysis as I continue with the program,” Scott said.
Revisiting Urban History Through Data
Another project, A Pioneer in Public Transit: New York’s Transition to Electrical Streetcars, was developed by Abhinav Chattaraj and Gill Woody. They investigated how the introduction and electrification of trolley systems influenced urban development, economic outcomes, and demographic patterns in New York City during the late nineteenth and early twentieth centuries. Their analysis combined census data with two historical maps , an 1880 Taunton map from the New York Public Library and an 1899 Colton, Ohman & Co. map from the Library of Congress. The researchers georeferenced in QGIS and traced by hand into a digital map of the streetcar network, all within a difference-in-differences framework. Their work examined the way in which proximity to streetcar lines shaped neighborhood composition , demonstrating the benefit of historical and spatial datasets that can reveal long-term patterns of urban transformation.
Mapping Energy Equity in New York State
Huiyuan Zheng and Xu Zhang explored the uneven geography of clean energy infrastructure in their project, Road to Energy Equity: The Spatial Mismatch between Renewable Production and EV Infrastructure in New York State.
Through geospatial analysis, the team investigated the disconnect between renewable energy production sites, such as wind and solar facilities, and electric vehicle charging infrastructure throughout New York State.
“Taking Professor Jung’s well-structured course has been an incredibly rewarding experience,” Zheng and Zhang said. “The lectures perfectly introduced us to the applications of spatial analysis in social sciences, while the lab sessions led by the two TAs gave us great hands-on practice with AI analysis methods. In this fast-evolving tech era, learning to embrace AI is essential; most importantly, this class empowered us to collect large-scale data and build our own datasets to address complex social issues, giving us the cutting-edge tools we need for future global development work.”
Their findings highlighted questions of fairness and equity within the clean energy transition. “We aimed to use data to address a neglected question: In the transition to clean energy, who is bearing the production costs and who is reaping the consumption benefits?” the team explained. “New York State serves as an ideal window for observation as a pioneer in climate policy. We suspected a spatial mismatch, with solar and wind facilities pushed into lower-income rural areas due to land availability, while EV charging clusters concentrated in wealthier urban cores, driven by income and market demand.”
After analyzing more than 5,000 census tracts across New York State, the researchers confirmed this pattern. “This means some communities bear the landscape costs of clean energy production while others enjoy most of the consumption benefits,” they said. “Without deliberate policy intervention, the green transition risks reinforcing old inequalities.”
Understanding AI Engagement in the Global South
Students S. M. Mehedi Zaman and Md. Mozammel Hoque investigated how geography shapes engagement with artificial intelligence technologies in the Global South.
Their project, A Spatial-Demographic Analysis of AI Engagement in the Global South, argues that location-based factors such as urban density and digital infrastructure may be stronger predictors of AI engagement than traditional demographic variables.
“The AI and Spatial Data Science course was a phenomenal class for me, as I had the chance to learn how to work with spatial data hands on,” said Zaman. “There were a lot of opportunities to learn from the research works of Dr. Jung, and also the TAs and students of the class. The course also helped us develop a robust final project, which we are planning to submit to an appropriate venue for publication.”
For Zaman, the interdisciplinary environment proved especially valuable. “For me, this course was really helpful for my research journey in Human-AI interaction, and I also got to learn about lots of amazing works from diverse backgrounds like economics, social work, and global development,” he said.
Hoque emphasized the course’s interactive and collaborative nature. “This was a special class not just because how Dr Jung taught us but also how she got us engaged with the content,” Hoque said. “We have had the chance to experiment with data and AI and spatial analysis technique to find out insights. This has created opportunity for me to research in the field of Human-AI relationship.”
He also reflected on the semester-ending presentations. “Finally, Dr Jung created the best experience for us to present our final projects before the class including guests from different schools,” Hoque said. “I wish the class will be brighter and better in next year too.” Through projects that span public health, transportation, environmental justice, and technology, AI & Spatial Data Science for Global Development demonstrates how interdisciplinary scholarship and emerging analytical tools can help researchers better understand and ultimately address complex social problems.
